{"id":"W4415460301","doi":"10.3390/higheredu4040065","title":"Harnessing Large Language Models for Scalable and Effective Formative Assessment in Higher Education: A Review","year":2025,"lang":"en","type":"article","venue":"Trends in Higher Education","topic":"Higher Education Learning Practices","field":"Social Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"The Scarborough Hospital; University of Toronto","funders":"Rhodes Scholarships","keywords":"Formative assessment; Context (archaeology); Transformative learning; Scalability; Higher education; Implementation","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01230551,0.0008705548,0.001595645,0.003957119,0.000408407,0.002725885,0.001664809,0.001495767,0.001873691],"category_scores_gemma":[0.0288871,0.0005412788,0.00142379,0.003678913,0.001184857,0.003304506,0.001515952,0.001498206,0.0008237541],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001504904,"about_ca_system_score_gemma":0.007351882,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00352937,"about_ca_topic_score_gemma":0.005587585,"domain_scores_codex":[0.994754,0.002321587,0.001061955,0.0004229367,0.001326979,0.0001126796],"domain_scores_gemma":[0.9563743,0.03753561,0.002174338,0.0006297245,0.003012604,0.0002733581],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00004958561,0.00007669606,0.0007161999,0.09898035,0.000221434,0.00006245284,0.0006993433,0.0007174755,0.0006060823,0.006414017,0.004028883,0.8874275],"study_design_scores_gemma":[0.00005784258,0.0005857663,0.005357491,0.20874,0.002216643,0.0008997211,0.001190153,0.001566564,0.002361685,0.00971343,0.7671322,0.0001784867],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.0005071674,0.9956917,0.001763075,0.0007183138,0.0001046853,0.00006831205,0.0000307113,0.00002501663,0.001091044],"genre_scores_gemma":[0.005641317,0.9889799,0.004582544,0.0003630463,0.00008744945,0.0001350602,0.00004175568,0.00001150535,0.0001573305],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.01230551,"threshold_uncertainty_score":0.06507856,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04975622032729901,"score_gpt":0.4643202307419215,"score_spread":0.4145640104146225,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}